Research Update and Future Work Directions – Jan 18, 2006 – Ognjen Arandjelović Roberto Cipolla.

Slides:



Advertisements
Similar presentations
GCAPS Status Report Ryan Weiss Nick Hebner Kooper Fram.
Advertisements

Part 2: Unsupervised Learning
Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Active Appearance Models
Learning deformable models Yali Amit, University of Chicago Alain Trouvé, CMLA Cachan.
Feature Selection as Relevant Information Encoding Naftali Tishby School of Computer Science and Engineering The Hebrew University, Jerusalem, Israel NIPS.
Object Recognition with Features Inspired by Visual Cortex T. Serre, L. Wolf, T. Poggio Presented by Andrew C. Gallagher Jan. 25, 2007.
Machine learning continued Image source:
Computer vision: models, learning and inference Chapter 18 Models for style and identity.
Sami Romdhani Volker Blanz Thomas Vetter University of Freiburg
Proposed concepts illustrated well on sets of face images extracted from video: Face texture and surface are smooth, constraining them to a manifold Recognition.
Online Multiple Classifier Boosting for Object Tracking Tae-Kyun Kim 1 Thomas Woodley 1 Björn Stenger 2 Roberto Cipolla 1 1 Dept. of Engineering, University.
Amir Hosein Omidvarnia Spring 2007 Principles of 3D Face Recognition.
Foreground Modeling The Shape of Things that Came Nathan Jacobs Advisor: Robert Pless Computer Science Washington University in St. Louis.
Robust Object Tracking via Sparsity-based Collaborative Model
Multiple View Based 3D Object Classification Using Ensemble Learning of Local Subspaces ( ThBT4.3 ) Jianing Wu, Kazuhiro Fukui
Face Recognition & Biometric Systems, 2005/2006 Face recognition process.
Face Verification across Age Progression Narayanan Ramanathan Dr. Rama Chellappa.
Motion Editing and Retargetting Jinxiang Chai. Outline Motion editing [video, click here]here Motion retargeting [video, click here]here.
Exchanging Faces in Images SIGGRAPH ’04 Blanz V., Scherbaum K., Vetter T., Seidel HP. Speaker: Alvin Date: 21 July 2004.
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
1 Color Segmentation: Color Spaces and Illumination Mohan Sridharan University of Birmingham
A Study of Approaches for Object Recognition
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
Incremental Learning of Temporally-Coherent Gaussian Mixture Models Ognjen Arandjelović, Roberto Cipolla Engineering Department, University of Cambridge.
Segmentation by Clustering Reading: Chapter 14 (skip 14.5) Data reduction - obtain a compact representation for interesting image data in terms of a set.
Automatic Face Recognition for Film Character Retrieval in Feature-Length Films Ognjen Arandjelović Andrew Zisserman.
Face Recognition from Face Motion Manifolds using Robust Kernel RAD Ognjen Arandjelović Roberto Cipolla Funded by Toshiba Corp. and Trinity College, Cambridge.
Classification and application in Remote Sensing.
Multiple Object Class Detection with a Generative Model K. Mikolajczyk, B. Leibe and B. Schiele Carolina Galleguillos.
An Illumination Invariant Face Recognition System for Access Control using Video Ognjen Arandjelović Roberto Cipolla Funded by Toshiba Corp. and Trinity.
Face Recognition and Retrieval in Video Basic concept of Face Recog. & retrieval And their basic methods. C.S.E. Kwon Min Hyuk.
Learning to classify the visual dynamics of a scene Nicoletta Noceti Università degli Studi di Genova Corso di Dottorato.
Computer Vision and Data Mining Research Projects Longin Jan Latecki Computer and Information Sciences Dept. Temple University
Face Alignment Using Cascaded Boosted Regression Active Shape Models
Multimodal Interaction Dr. Mike Spann
1 Mean shift and feature selection ECE 738 course project Zhaozheng Yin Spring 2005 Note: Figures and ideas are copyrighted by original authors.
Graphite 2004 Statistical Synthesis of Facial Expressions for the Portrayal of Emotion Lisa Gralewski Bristol University United Kingdom
A General Framework for Tracking Multiple People from a Moving Camera
LOGO On Person Authentication by Fusing Visual and Thermal Face Biometrics Presented by: Rubie F. Vi ñ as, 方如玉 Adviser: Dr. Shih-Chung Chen, 陳世中.
Visual Tracking Conventional approach Build a model before tracking starts Use contours, color, or appearance to represent an object Optical flow Incorporate.
1 Recognition by Appearance Appearance-based recognition is a competing paradigm to features and alignment. No features are extracted! Images are represented.
Combined Central and Subspace Clustering for Computer Vision Applications Le Lu 1 René Vidal 2 1 Computer Science Department, Johns Hopkins University,
An Information Fusion Approach for Multiview Feature Tracking Esra Ataer-Cansizoglu and Margrit Betke ) Image and.
Spatio-temporal constraints for recognizing 3D objects in videos Nicoletta Noceti Università degli Studi di Genova.
Fast Similarity Search for Learned Metrics Prateek Jain, Brian Kulis, and Kristen Grauman Department of Computer Sciences University of Texas at Austin.
Object Recognition in Images Slides originally created by Bernd Heisele.
Learning the Appearance and Motion of People in Video Hedvig Sidenbladh, KTH Michael Black, Brown University.
MSRI workshop, January 2005 Object Recognition Collected databases of objects on uniform background (no occlusions, no clutter) Mostly focus on viewpoint.
PSEUDO-RELEVANCE FEEDBACK FOR MULTIMEDIA RETRIEVAL Seo Seok Jun.
Face Detection Ying Wu Electrical and Computer Engineering Northwestern University, Evanston, IL
Face Detection Using Large Margin Classifiers Ming-Hsuan Yang Dan Roth Narendra Ahuja Presented by Kiang “Sean” Zhou Beckman Institute University of Illinois.
EE4-62 MLCV Lecture Face Recognition – Subspace/Manifold Learning Tae-Kyun Kim 1 EE4-62 MLCV.
The Viola/Jones Face Detector A “paradigmatic” method for real-time object detection Training is slow, but detection is very fast Key ideas Integral images.
Image Classification for Automatic Annotation
CAMEO: Face Recognition Year 1 Progress and Year 2 Goals Fernando de la Torre, Carlos Vallespi, Takeo Kanade.
CHAPTER 1: Introduction. 2 Why “Learn”? Machine learning is programming computers to optimize a performance criterion using example data or past experience.
Data Mining, ICDM '08. Eighth IEEE International Conference on Duy-Dinh Le National Institute of Informatics Hitotsubashi, Chiyoda-ku Tokyo,
Video Databases What are it uses? –Sports –Surveillance How do we query it? –Mosaic-based Query Language.
Robust Localization Kalman Filter & LADAR Scans
1 Kernel Machines A relatively new learning methodology (1992) derived from statistical learning theory. Became famous when it gave accuracy comparable.
Learning Image Statistics for Bayesian Tracking Hedvig Sidenbladh KTH, Sweden Michael Black Brown University, RI, USA
1 Bilinear Classifiers for Visual Recognition Computational Vision Lab. University of California Irvine To be presented in NIPS 2009 Hamed Pirsiavash Deva.
MIT Artificial Intelligence Laboratory — Research Directions Intelligent Perceptual Interfaces Trevor Darrell Eric Grimson.
Intrinsic images and shape refinement
Machine Learning Basics
Paper Presentation: Shape and Matching
Outline H. Murase, and S. K. Nayar, “Visual learning and recognition of 3-D objects from appearance,” International Journal of Computer Vision, vol. 14,
Unsupervised Learning of Models for Recognition
Patch-Based Image Classification Using Image Epitomes
Presentation transcript:

Research Update and Future Work Directions – Jan 18, 2006 – Ognjen Arandjelović Roberto Cipolla

Overview Research update: 1. Face recognition from video for i.User authentication ii.Multimedia retrieval/organization 2.Acquisition conditions-adaptive image filtering 3.Local manifold illumination-invariants

AFR from Video: Authentication (ECCV) Key ideas: Sequence re-illumination algorithm Offline learning: generic effects of illumination across human face shape variation Addressed invariance to: 1.Illumination 2.Pose 3.User motion pattern

AFR from Video: Authentication (ECCV) Key results: Average recognition 99.7% on 171 people (over 1300 sequences) Excellent generalization, even across race Interesting findings on image filters for AFR Future work: Efficiency improvement (more compact representations of FMMs…) Smarter use of image filters (different research direction)

Automatic Cast Listing in Films (CVPR) Visually defined clustering – on face appearance manifolds Key ideas: Similarities between people exhibit coherence – exploited by working in the Manifold Space (each point a manifold) Iterative unsupervised learning, bootstrapped using offline training

Automatic Cast Listing in Films (CVPR) Key results: Algorithm needs more testing – only preliminary results in Very promising improvement over simple clustering (inter-manifold distance thresholding) “Simple clustering” results My clusters Single cluster

A New Look at Filters for AFR (FG) Key ideas and methods: Recognition performances of raw and filtered data negatively correlate (ECCV results) Learn how to optimally combine raw input and filtered data Implicit learning of the severity of data acquisition conditions We propose a heuristic, iterative algorithm

A New Look at Filters for AFR (FG) A summary of the results:

Local Manifold Illumination Invariant (ICPR) Method overview: Consider the generative function of the face appearance manifold We show that the angles between hyperplanes of small head motion are invariant under illumination changes Manifold is represented as a redundant set of locally linear patches

Probabilistic Extension of MSM (ICPR) MSM limitations: Information loss with subspace dimensionality choice Within subspace, all directions treated the same – decreased SNR Key idea: Find the most probable “mutual mode” Efficiently computed similarity:

Colour invariants for AFR Key ideas: Colour used extensively for detection applications – very little research on its use for recognition Step 1: Model non-linear response of the photometric sensor Step 2: Recover model parameters Step 3: Camera/illumination invariants

AFR for Content-Based Retrieval and Synthesis Combine: Face recognition Texture/Segmentation Local features-based retrieval Image mosaicing Retrieval query interface tool